corehu
Rent a GPU

USE CASE

Run Llama and other open LLMs on a cloud GPU

Chat with Llama, Qwen or Mistral, or serve them over an API with Ollama. The Ollama template starts the server for you.

See RTX 4090 machines Checking live prices…

Billed per second from your USD balance. Stop or terminate the machine when you are done.

Recommended GPU

RTX 4090 · RTX 5090 · A100 SXM4

8B–14B models fit on a 24 GB RTX 4090. For 32B–70B models pick an RTX 5090 or an A100 80 GB.

Template to pick

Ollama

Run LLMs with a single command; OpenAI-compatible API included.

Up and running in four steps

  1. 1

    Rent the machine

    Open the catalog with the Ollama template already selected, pick a GPU and press Rent.

    See RTX 4090 machines
  2. 2

    Connect with SSH

    Copy the SSH command from your machine's page. Add the port forward if you want to call the API from your computer.

    ssh -p <PORT> root@<HOST> -L 11434:localhost:11434

    The SSH command is on your machine's page. The -L part forwards the port so the app opens in your own browser.

  3. 3

    Download and chat with a model

    Ollama is already running. Pull a model and start chatting.

    ollama run llama3.1:8b
  4. 4

    Use the API

    Ollama speaks an OpenAI-compatible API on port 11434.

    curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"llama3.1:8b","messages":[{"role":"user","content":"Hello"}]}'

Questions

Is my data used to train anything?

No. The model runs on your rented machine; prompts and outputs stay on it.

Can I use it from my app?

Yes. Point an OpenAI-compatible client at http://localhost:11434/v1 through the SSH tunnel.